# Computational discovery of high-temperature superconducting ternary hydrides via deep learning

## TL;DR

This paper uses deep learning to discover new high-temperature superconducting hydrides, identifying over 100 new compounds and 27 new structures.

## Contribution

A deep-learning framework that enables efficient discovery of high-temperature superconducting ternary hydrides and novel structural prototypes.

## Key findings

- Over 129 new superhydrides with critical temperatures above 200 K were identified.
- 27 novel structural prototypes for hydride superconductors were discovered.
- The approach explores 36 million structures across 29 elements under 200 GPa.

## Abstract

The discovery of novel high-temperature, or even room-temperature, superconducting materials holds transformative potential for a wide array of technological applications. However, the combinatorially vast chemical and configurational search space poses a significant challenge for both experimental and computational investigations. In this study, we employ the design of high-temperature ternary superhydride superconductors as a representative case to demonstrate how this challenge can be effectively addressed through a deep-learning-driven theoretical framework. This framework integrates high-throughput crystal-structure exploration, physics-informed screening and accurate prediction of superconducting critical temperatures. Our approach enabled the exploration of approximately 36 million ternary hydride structures across a chemical space of 29 elements, leading to the identification of 144 potential high-\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
$T_{\rm c}$\end{document} superconductors with predicted \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
$T_{\rm c} \ge 200$\end{document} K and superior thermodynamic stability at 200 GPa. Among these, 129 compounds spanning 27 novel structural prototypes are reported for the first time, representing a significant expansion of the known structural landscape for hydride superconductors. This work not only greatly expands the known repertoire of high-\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
$T_{\rm c}$\end{document} hydride superconductors but also establishes a scalable and efficient methodology for navigating the complex landscape of multinary systems.

High-throughput crystal structure searches (CSP) performed by DPA-based large atom model (LAM) and Tc prediction model enabled the discovery of over 129 new superhydrides and 27 new prototypes.